Presented By
O’Reilly + Cloudera
Make Data Work
29 April–2 May 2019
London, UK

Machine learning from scratch in TensorFlow

Ana Hocevar (The Data Incubator)
Monday, 29 April & Tuesday, 30 April, 9:00 - 17:00
Data Science, Machine Learning & AI
Location: Capital Suite 9
Secondary topics:  Deep Learning
Average rating: ****.
(4.38, 8 ratings)

Participants should plan to attend both days of this 2-day training course. To attend training courses, you must register for a Platinum or Training pass; does not include access to tutorials on Tuesday.

The TensorFlow library provides for the use of computational graphs, with automatic parallelization across resources. This architecture is ideal for implementing neural networks. Ana Hocevar offers an intro to TensorFlow's capabilities in Python, taking you from building machine learning algorithms piece by piece to using the Keras API provided by TensorFlow with several hands-on applications.

What you'll learn, and how you can apply it

  • Understand what machine learning, neural networks, deep learning, and artificial intelligence are
  • Discover what TensorFlow is and what applications it's good for
  • Learn how to create deep learning models for classification and regression using TensorFlow
  • Evaluate the benefits and disadvantages of using TensorFlow over other machine learning software

This training is for you because...

  • You want to learn about deep learning and neural networks in TensorFlow.

Prerequisites:

  • A working knowledge of Python
  • Familiarity with matrices, modeling, and statistics
  • No experience with TensorFlow required

Hardware and/or installation requirements:

All you'll need is your own laptop that is running either a Chrome or Firefox browser. Upon arriving at the training, you will be given login information for your individual cloud instance, which you will be working from for the duration of the course.

Outline

Day 1

  • Introduction to TensorFlow
  • Iterative algorithms
  • Machine learning
  • Basic neural networks

Day 2

  • Deep neural networks
  • Variational autoencoders
  • Convolutional neural networks
  • Adversarial noise
  • DeepDream
  • Recurrent neural networks

About your instructor

Photo of Ana Hocevar

Ana Hocevar is a data scientist in residence at the Data Incubator, where she combines her love for coding and teaching. Ana has more than a decade of experience in physics and neuroscience research and over five years of teaching experience. Previously, she was a postdoctoral fellow at the Rockefeller University, where she worked on developing and implementing an underwater touchscreen for dolphins. She holds a PhD in physics.

Conference registration

Get the Platinum pass or the Training pass to add this course to your package.

Comments on this page are now closed.

Comments

Picture of Ana Hocevar
Ana Hocevar | DATA SCIENTIST
15/01/2019 15:52 GMT

You should be fine! Looking forward to meeting you!

Yonnie Kirzon |
15/01/2019 15:08 GMT

Hi,
I would like to register to this training but wanted to make sure – what’s the level of familiarity needed for matrices modelling and statistics?
I am not unfamiliar with these topics, but never really worked with statistics and modelling that much. I think I can manage but don’t want to feel “behind” during the training sessions.

Thanks